openspec-archive

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via the processing of external data.\n
  • Ingestion points: The skill reads delta specification files from the openspec/changes/ directory into the agent's context.\n
  • Boundary markers: No specific delimiters or instructions for the agent to ignore instructions embedded within the processed spec files are mentioned.\n
  • Capability inventory: Performs file merge operations into openspec/specs/ and moves directories to openspec/changes/archive/.\n
  • Sanitization: Lacks explicit content validation or sanitization of spec file content before merging data into the project's source of truth.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:35 PM